This repository is the implementation of AA-AEGD, see the paper from https://arxiv.org/abs/2211.08578v1. The codes show the performance of AA-AEGD on the quadratic and rosenbrock functions, and the problems of machine learning (ML). As for the cases of quadratic function and ML, we adapted the codes from https://github.com/vienmai/AA-Prox. More detail about AEGD https://github.com/txping/AEGD.
-
Notifications
You must be signed in to change notification settings - Fork 1
howardjhe/AA-AEGD
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
This repository is the implementation of Anderson acceleration for "adaptive gradient descent with energy" (AEGD).
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published